วีดีโอ

Glad I could help.😊

As far as I know, there are none in India..

Ohh yes.. I had set it to 2 before. Not sure when I set it back to 0. 🤔 But thanks for this. I will update the article again. 😄

Does it have PSRam on it? Usually the pin numbers are displayed on the board.

Thank you so much for such kind words. Glad I could help. 😊

Of course you can.. in the assist pipeline, change the voice for the text to speech .

Thank you so much for your kind appreciation. 😃. Definitely helps me keep going.

May I add I stumbled initially once the device was set up, the problem I found was I had to go into voice assistant settings and set up a new assist profile, then leaving wake word empty

@@nigelbye7965 ohh yes.. you have to not set any wake word in the assist pipeline.

It's not in my add-ons but it is in my integrations (devices & services, integrations), when I'm trying to configure the integration it asks me for a server address which is already there by default, I press the send button and then show me "Failed to connect" prompt

Ohh yes.. Missed that. I'll update the article. Thank you 😊

Yes.. I know this error. So you will have to extend the free subscription of the cloud development plan. Here is the link to it : support.tuya.com/en/help/_detail/Kc3n6kr7kllhc

Glad I could help 🙂

None that I have seen. Also the issue of the cracking sound on boot has disappeared that existed in the ESP32 setup.

I think this is because of the latest update of ESPhome 2024.05. It has broken the Voice assistant. I will try to find a solution. Haven't got to it yet. If you are blocked, you can try reverting ESPHome update to 2024.04 and it should be fine. Or you can check my latest video on the ESP32 S3 with on-device Wake word. th-cam.com/video/aPP2alIU7Gg/w-d-xo.html

Thank you glad it’s not just me

First of all, nice to see you are using AI for the responses. Kudos on that. 👍 I was trying to make the same for work for me. But it was not very reliable. Will try ollama this time. To answer your question, To get a better sounding speaker, I haven't got one, but may be you can redirect the audio from the response to alexa or google home mini. Check this video th-cam.com/video/RIpnyTJmJJ8/w-d-xo.html . I haven't tried it with this device, but it was working well with my older voice assistant with an ESP32 I had to use the resistor to reduce the volume as I could not adjust the level in Home Assistant. To provide volume controls, we have to use `media_player` type, but its not supported for IDF frameworks. Hence the option was the resistor.

@@SmartHomeCircle Thx for your Feedback. Why Alexa or Google home, why not a Bluetooth speaker ?

Bluetooth speakers are difficult to connect to Home Assistant. The cast option with google mini allows for easier integration.

I am glad the video helped. 🙂 My German is not that good, but I what I understood is that the voice response is incomplete or gets stuck. I dint face issues with the response being incomplete or stuck. I had problems with the speaker crackling on boot, so I moved the amplifier input from 5v to 3.3v , as I think the LED strip was interfering with it. Does that give you some help?

Genau das Problem es bricht einfach ab

Glad I could help 🙂

Glad I could help 🙂

No.. it's currently not possible with the speaker type in the yaml. And media_player is not supported for idf frameworks

@@SmartHomeCircle thanks, btw can i use the same i2c pin for light sensor (bh1750) or temp sensor (ath10)

I think you could use it, but you will have to try it out. I remember when I was using the light the co2 sensor, I had to make use of daisy chain connection for it to work. Check this video : th-cam.com/video/bwVttXh4Lk4/w-d-xo.html I would say first try with normal parallel connection and if it does not work, then try the daisy chain connection approach. Hope this helps.

Glad you liked it. 😊

What type of button is it and where do I connect it to on the board?

The circuit diagram in the article shows how to connect the mute button. This is the button I used : s.click.aliexpress.com/e/_DEhJfB1

Checked the article and definitely does not show the button in the parts list the circuit diagram or connection list. It’s in the yaml GPIO10 but where do I connect the other wire? Sorry to be a pain. p.s. I love your work and have been building your things for sometime

I watched the video and managed to pause it at the exact point where I could see it’s connected to GND

I could get it to work around 3 mts away. So good for a room..

Its an internal IP so its fine.

@@SmartHomeCircle I meant you don't need any IP scanners, if you have ESPHome console. :)

@@formatBCE ohh yes.. good point. For me since I run esphome using docker, the auto discovery fails because of absence of mDNS. Hence I would usually need the ip scanner.

@@SmartHomeCircle yeah i have mDNS turned off too. What i actually meant, when you open device logs in your ESPHome dashboard, it reports system info (purple lines), and among that lines there's current IP address - so you can take it from there instead of guessing from long list of unknown IP addresses in IP scanner. For myself, i have big pool of static IP addresses, that i use for my smart devices. This way i always know that my DHCP lease didn't expire and device didn't change their IPs.

@@formatBCE ohh yes.. I use static IPs too. It's just in the video that I didn't want it to be more complex with static IPs.. as different folks would have different subnets configured in the router. So I tried to at least give people a tool that shows a blue icon next to an active ip address and test if it belongs to the device.

As far as I know, the voice is captured from that hole. You might have to check how clearly the voice gets recorded with it.

Do you mean 200 devices in Home Assistant? I haven't got so many devices yet😄 If you use the assist window and try to write a command to invoke one of those 200 devices, and if that is fast then it would be fast also. This device just takes the input and gives it to HA.

It will be just fine. If you mean voice satellites - it's good to have local wake word, otherwise they all would be bombing HA with audio streams to find wake word.

@@formatBCE Yes, true. reduces some resources on the HA server also.

Thanks heaps, followed all your previous videos successfully, so looking forward to starting on this one

@@clairerovic thank you 🙂

I think you are talking about custom wake words, I will be working on that for my next video.

AFAIK to setup custom wake word for microwakeword, you'll have to train it in pretty specific way. Also i can't see the mechanism of setting it in the configuration so far - it seems like microwakeword is pointing to ESPHome GitHub, where these words are.

I didn't understand the question..

Have you been using the device for sometime? Or is this the first time you are logging in?

@@SmartHomeCircle first time log in. Now I get to log in but it often comees back. Thinking the network is bad

I think I did face such an issue sometime back. I think that happened to me when I abruptly turned of the device( actually by mistake while rearranging the power supply connections to all the devices) The only way I got it back to work back again was a restart, and it was back to normal. I am currently using OMV with a NVMe drive every day to edit my videos and dint get the same problem again. Ill be making a new video on new NAS setup with the Pi.

You can copy it from this article here : smarthomecircle.com/how-to-connect-wifi-to-home-assistant-on-startup

The wake word detection is very instantaneous. No delays at all. Understanding the commands after that depends on speech to text model and how powerful the machine is. I have switched completely to this setup and will be releasing a new video of my personal voice assistant version 2.

@@SmartHomeCircle Thx for answering.

If there were issues with wake word detection with the ESP32 then this is really stable and instantaneous. However if detecting converting the voice command after the wake word detection, that would depend on which speech to text model you have and the machine you are running on. I am using this setup now and replaced my older esp32 setup. Found it much better. So a new video will be coming out soon of my Voice Assistant version 2 😄

Will wait for your Video part-2. I am running STT on the same machine as the HA one. Probably this could be the issue. I am trying Home Assistant Cloud and that works well. I have tried Azure cloud also and that is equally fine. But it defeats the very purpose of this exercise, i.e local voice assistant. Is there any other Local STT better than whisper. Tried Vosk without much success.

If you have a better higher performance machine, then it works fine. I bought a refurbished one from ebay for like 100 euros. I5 6500T, quad core, 16 GB ram and I am running Whisper on it. It is pretty reliable for me after using the small-int8 model. It's quick to respond like in 1-2 secs and has a 90% success rate.

Do you mean by audio pipeline as in piper?

Can you tell me what is broken?

Ahh, I see it stops working after the first command. Ill try to find a fix for this. I am currently using the on-device wake word detection which I felt is much more reliable. Here is the link : th-cam.com/video/rT_q0g8dtmY/w-d-xo.html

Thanks for you work man. Unfortunately I am experiencing the same issue; it works only once and then stops. I am forced to reload the integration. Than there is that terrible sound.. I'm interessed also to your project with ESP32-S3.

Having the same issue as well, stops after the first command. Tried several things with no luck, turned on debugging, did not see any issues. I have an S3 and can make your new design but this device was working perfectly with my custom wake word, no false positives. If a new release of ESPHome does not come out soon, I will move to on-device S3. I see M5 Atom Echo users are having issues too. Hope you can figure it out.

Do you mean for other in built intents? Or you want have a custom response for the automation you created?

I have solved it. When I create the automation I can add a custom response also. Thanks

Ohh yes.. the custom response is easier.

Yes.. Of course you can.. 😃 You have to set it via the Home Assistant UI, by going to settings > System > Network. This video is just if you dont have a wired connection around you.

With this device, Its not possible to have a separate sensor attached to it. The only way would be to use some sort of automation in Home Assistant.

There is no access to addons while running Home Assistant as a container.

@@SmartHomeCircle I was under the impression you were using the dockerized version of HA, I didn't realize you were using it only for the wyoming satellite.

@@invdrzim5600 I personally use the the Docker version of HA. But in this video I was using the HA OS. Also addons are basically docker containers run by Home Assistant. So I also run some of them using the docker command. But it's very tedious to do that. If you are familiar with docker, you can check the HA addons github repo, to find the command to run. But its still a hit or miss. So HA OS is the easiest option.

I am a little not sure about this. I havent played around with 2 channel switches.

Currently no. The blueprint that I have mentioned in the article is the only solution that is the fastest.

Yes.. I know this error. So you will have to extend the free subscription of the cloud development plan. Here is the link to it : support.tuya.com/en/help/_detail/Kc3n6kr7kllhc

You have to first enable ssh for the user in OMV. For this go to users, then the user you will use to perform the ssh, click on edit and add then add the _ssh group to the user. You should then be able to ssh.

Configure homemate devices using tuya and integrate using localtuya.

I will be making a video for that soon. Currently via the ui, its not possible.. may be via ssh , you can use the unmount command..